The longitudinal control for a platoon of connected and automated vehicles is a popular topic in transportation engineering, nowadays. However, a majority of existing results about the cooperative/distributed platoon control are based on linear models that are derived from nonlinear vehicular dynamics by exact feedback linearization. This nonlinear–linear transformation asks for a complete priori knowledge of vehicular dynamics, which could be difficult to obtain in practice. To overcome this disadvantage and address multiuncertainties including both unknown plant parameters and unknown control coefficients in third-order vehicular node dynamics, this paper proposes a distributed backstepping control scheme in a networked environment. Unknown parameters are identified online, and both internal stability and string stability for constant distance spacing policy are established. Simulation studies are carried out by comparing the adaptive control proposed in this paper with the robust control in the state-of-the-art algorithms.

Most existing studies modeled Adaptive Cruise Control (ACC) car-following (CF) behavior using conventional CF models which were originally built for human-driving vehicles (HVs) and calibrated with HV data. In this paper, firstly a learnable CF model is proposed by resorting to Long Short-Term Memory (LSTM) for ACC systems, which utilizes the ACC data for model construction and offers extraordinary adaptability and accuracy. Nevertheless, the applicability of the LSTM CF model is hindered by the scarce ACC data problem, as training the model requires a large amount of data. To address the ACC data scarcity problem, a transfer learning strategy for the LSTM model is further developed, leveraging on the large-scale open-source HV data and the similar driving patterns hidden in HV and ACC-equipped vehicles. In the transfer learning based LSTM model, a unified framework incorporating an alignment layer is developed to transfer the useful features from HV data and meanwhile calibrating the CF model with ACC data. Comparison results show that the proposed model outperforms other CF models which are built with only ACC data or using simple transfer learning methods. Further, microscopic simulations are performed to verify the applicability of the transfer learning based LSTM CF model.